Diffus
Get started
models/PixelWave - FLUX.1-schnell 04

PixelWave - FLUX.1-schnell 04

humblemikey
|
12/27/2025
|
6:02:59 AM
| Discussion
An astronaut in a weathered spacesuit stands in a white desert before a massive shark-shaped starship with a gaping mouth-like opening and large engines.

Recommended Parameters

samplers

Euler Normal, dpmpp 2m sgm uniform, dpmpp_2s_ancestral, Euler, DPM++ SDE, 2M SDE Karras

steps

4 - 40

cfg

2.5 - 7

resolution

1536x1536, 1024x1024

vae

ae.safetensors

Recommended Hires (High-Resolution) Parameters

upscale

1.5 - null

Tips

Use more than 8 steps to improve finer details, but output does not change much after 8 steps.

Adding style prompts can help model generate neater and cleaner output.

Try increasing guidance scale to get cleaner images.

Avoid using 'quality' terms such as 4K, 8K, masterpiece, high def if you want a natural look in photography.

For upscaling, try upscale latent by node and scale latent by 1.5 for higher resolution images.

Use pagedlion8bit optimizer for training on 24GB GPU, frozen time_in, vector_in, and modulation parameters to prevent de-distillation.

Stop training at few thousand steps with LR 5e-6 to avoid corrupt blocks and block merge with earlier checkpoints to fix corruption.

Version Highlights

Fine tune of schnell model, not using the dev model in anyway. Apache 2.0 license!

Trained with kohya using a custom sigma schedule and freezing time and modulation parameters to prevent degradation of time distillation.

➤ Combined training steps : 1,360,641

➤ Active training time: 1192.61 hours (49.7 days)

Creator Sponsors

Model also available at: RunDiffusion and Runware.ai

Huge thank you to RunDiffusion for sponsoring the compute for training this model!

For API access, check out Runware.ai.

PixelWave FLUX.1-schnell 04 - Apache 2.0!

Safetensor Files: 💾BF16 💾FP8 💾bnb FP4

GGUF Files: 💾Q8_0 🤗Q6_K 💾Q4_K_M

Links to 🤗VAE 🤗T5xxl 🤗CLIP L

Model also available at: RunDiffusion and Runware.ai

PixelWave FLUX.1 schnell version 04 is an aesthetic fine tune of FLUX.1-schnell. The training images were hand picked to ensure the model has a bias to eye catching images, with beautiful colors, textures and lighting.

  • Trained on the original schnell model, so Apache 2.0 license!

  • No special requirements to run. Supports FLUX LoRAs

  • Euler Normal, 8 steps.

You can use more steps to improve finer details, but the output doesn't change much after 8 steps.

Shout out to RunDiffusion

Huge thank you to RunDiffusion (co-creators of Juggernaut) for sponsoring the compute that made training this model possible! Figuring out how to train schnell without de-distilling the model required a lot of experimenting, and being able to utilize RunDiffusion's cloud compute made it a lot easier.

For those needing API access for this model, we're partnering with Runware.ai

I have made the FLUX.1-dev 04 version exclusive to RunDiffusion and Runware for the time being. When I release version 05 in future, I plan to release the dev 04 open weights.

Grateful for their support in getting this model out there, please check them out!

Training

Training was done with kohya_ss/sd-scripts. You can find my fork of Kohya here , which also contains changes to the sd-scripts submodule, make sure you clone both.

Use the fine tuning tab. I found the best results with the pagedlion8bit optimizer which also could run on my 4090 GPU 24GB. I found other optimizers struggle to learn anything.

I have frozen the time_in, vector_in and mod/modulation parameters. This stops the 'de-distillation'.

I avoid training single blocks over 15. You can set which blocks to train in the FLUX section.

LR 5e-6 trains fast, but you have to stop after a few thousand steps as it starts to corrupt blocks and slow down learning.

You can then block merge with an earlier checkpoint, replacing the corrupt blocks, and then continue training further.

Signs of corrupt blocks: paper texture over most images, loss of background details.

Contact

For business or commercial inquiries please reach out to us at pixelwave@rundiffusion.com. Licensing flux fine tunes. Customer training projects. Commercial AI development. The team can do it all!

PixelWave Flux.1-dev 03 fine tuned!

Safetensor Files: 💾BF16 💾FP8 💾NF4

GGUF Files: 💾Q8_0 🤗Q6_K 💾Q4_K_M

Links to 🤗VAE 🤗T5xxl 🤗CLIP L

The 'diffusers' files are actually the Q8_0 and Q4_K_M GGUF versions. GGUF files also available on huggingface.

I fine tuned version 03 from base FLUX.1-dev for over 5 weeks on my 4090. It is able to do different art styles, photography, and anime. Trick I discovered to help with LoRAs.

I used dpmpp 2m sgm uniform 30 steps for the showcase images. If you want a neater/cleaner output, try increasing the guidance. Also mentioning a style can help, so the model doesn't have to guess.

I also recommend try adding the upscale latent by node, and scale the latent by 1.5, e.g. generating an image that is 1536x1536 instead of 1024x1024.

PixelWave Flux.1-schnell 03

Safetensor Files: 💾FP8 💾NF4

GGUF Files: go to huggingface

I used dpmpp 2m sgm uniform 8 steps for the showcase images.

You can start with 4 steps, but there are less errors with anatomy if you run with more steps.

PixelWave Flux.1-dev 02

Safetensor Files: 💾BF16 💾FP8

GGUF Files: 💾Q8_0 🤗Q6_K 💾Q4_K_M

Version 02 has greatly improved black and dark images, and more reliable outputs with fewer issues with hands.

I recommend using dpmpp_2s_ancestral, beta, 14 steps. Or euler, simple, 20 steps.

Comfyui-GGUF Nodes

PixelWave 11 SDXL. A general purpose fine tuned model. Great for art and photo styles.

I use 20 steps, DPM++ SDE, CFG 4 to 6 or 40 steps, 2M SDE Karras

Accelerated Version - 5+ Steps, DPM++ SDE Karras, 2.5 CFG

PAG Recommended⚡Recommend 1.5 Scale, with CFG 3. Link to workflow

🔗Link to Expanded Gallery 🖼️

⭐Link to prompting guide.⭐ You don't need to use 'quality' terms such as 4K, 8K, masterpiece, high def, high quality, etc. Unless you want it, I recommend not using words such as 'vibrant, intense, bright, high contrast, neon, dramatic' for photographic styles if you a wanting a more natural look. This can cause images to look 'overcooked', but it's just the CLIP following your prompt. 🙂 If you do want vibrant, neon photos PixelWave will provide!

The focus for version 10 was to train the CLIP models, which improves the reliability, ensures you can produce a wide variety of styles, and better at following prompts.

Thanks to my friends who helped test: masslevel, blink, socalguitarist, klinter, wizard whitebeard.

Guide: Upscaling Prompts with LM Studio and Mikey Nodes

Guide: Add more details to your image using the skip step method

No need for the refiner model.

This model is not a mix of other models.

I also created Mikey Nodes which contains a lot of useful nodes. You can install it through comfy manager.

Contributor

humblemikey avatar

humblemikey

Previous
Smol Dragons [LoRA 1.5+SDXL] - SDXL
Next
ICBINP - "I Can't Believe It's Not Photography" - LCM
Use this model

Model Details

Model type

Checkpoint

Base model

Flux.1 S

Model version

FLUX.1-schnell 04

Model hash

565b846820

Creator

humblemikey's avatar
humblemikey

Discussion

Please log in to leave a comment.

Images by PixelWave - FLUX.1-schnell 04

An astronaut in a weathered spacesuit stands in a white desert before a massive shark-shaped starship with a gaping mouth-like opening and large engines.

anime Images

Scenic Scandinavian lake surrounded by dense forest under a vibrant orange sunset sky, with clouds reflected in the water and mountains in the background.
Overhead view of soft, rolling sand dunes in a vast Scandinavian desert under a warm orange sunset sky with birds soaring above, illustrated in anime style.
A photorealistic depiction of a woman with long white hair and red eyes, wearing black textured armor and metal cuffs, posed with clawed hands and red nails against an abstract red and white background featuring crosses.
A neon-haired anime girl with pastel pink and blue hair, wearing a shiny yellow and blue retro-futuristic jacket, posed against a dark sky blue gradient background.
A woman in a flowing white dress dances barefoot on a giant piano keyboard surrounded by swirling floating sheet music under a bright blue sky.
Close side view of a traditional wooden longtail boat with vibrant pink, orange, yellow, blue, green, and red fabric garlands wrapped around its dark brown prow, floating on pale green tropical water near a sandy shore, with limestone karst mountains and a bright blue sky with scattered clouds in the background.
A girl stands on a circular stone platform surrounded by shattered glass shards flying upward through a large circular stone portal, set in a dreamy space with broken glass platforms and a blue sky.
Anime-style young woman dressed in tactical gear and a worn headscarf standing against a stark desert background with rocky formations under a clear sky.
A detailed red flower with black and gold leaves blends into a cosmic abstract background of constellations, swirling gold and black patterns with light particles.
A young woman in an anime style stands in a neon-lit city street, fragmented by digital glitch art with vibrant pink and blue hues.

base model Images

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky cemetery illuminated by glowing jack-o'-lanterns under a dark, ominous sky.

digital art Images

Digital portrait of a female with black hair and detailed amber eyes, wearing translucent clothing, surrounded by colorful floating ribbons on a simple background.
A photorealistic surreal scene of a giant white octopus with strange scales and tentacles on a tanker deck surrounded by silhouetted fishermen under green lighting and sunshine.
A sleek futuristic vehicle with bright headlights sits centered on a dark road stretching through towering cyberpunk skyscrapers under an orange glowing sky.
Photorealistic futuristic female robot with rabbit-like ears, adorned with pink floral patterns on a white and blue mechanical body, shown from a profile view against a beige background.
Digital artwork of a chrome skeleton wearing a white leather jacket with a hood, holding a futuristic rifle against a solid red background.
Girl sitting wearing a white dress with a hood featuring cat ears, white pantyhose, dark blue frilly socks, and large black platform shoes
Dark cyberpunk mythical creature with glowing red eyes and neon blue highlights, featuring detailed 3D rendering and surreal digital art effects.
A beautiful cyborg woman with a robotic arm and neck, wearing a binary code patterned shirt, sitting inside a futuristic car with neon city lights in the background.
Close-up digital art of a girl with long dark hair and bangs, glowing hypnotic pink eyes, and a striped shirt against a vibrant psychedelic swirl background of orange and purple hues.
Cyberpunk style humanoid robot with a glossy black exoskeleton and glowing wires stands against a futuristic neon-lit cityscape at night.

photography Images

Close-up portrait of a redhead woman with blue eyes and dramatic lighting, featuring a flamboyant hairstyle and sun tanned skin against a blurred dark background.
Cyberpunk female android warrior with white hair, black armor with gold and orange glowing accents, holding a large sword vertically in front of her face against a black background.
A futuristic cyborg girl with luminous neon white hair and mechanical limbs sits cross-legged on the ground, illuminated by cinematic lighting with a dark, starry urban background.
Full-body figure wearing an orange hoodie and black jogger pants with a bored face emoji mask, standing sideways in a minimalistic open space with blurred figures in motion around.
A futuristic robot girl with metallic skin and a blonde braid stands on the moon's surface, holding a glowing star with Earth and a large moon in the background under a starry sky.
Man in jean shorts and white tank top drinking a can of beer while pushing a lawn mower in a suburban yard with a white fence, American flag waving, and a golden retriever chasing a ball.
Highly detailed, realistic full body portrait of Pikachu with cinematic lighting, showing it in sharp focus on a dark background.
Beautiful blonde maid with blue eyes and short hair in a detailed white and black maid outfit, standing by a window overlooking Tokyo city.
Close up portrait of an extraordinary Blue Jay bird at dawn featuring detailed feathers, vibrant blue crest, and sharp eye with subtle motion blur.
Blonde woman with freckles and smile sitting outdoors wearing a maroon v-neck t-shirt and floral microskirt under natural lighting

traditional art Images

A determined girl wearing a white hooded cloak crouches in a narrow alley holding a sword illuminating the ground with dramatic sunlight, painted in a traditional style.
A confident female Roman guardswoman wearing intricately detailed bronze battle armor, standing in a historic city street setting during daylight.
Oriental ink wash painting depicting dramatic waterfalls cascading through rugged mountain cliffs with misty atmosphere and faint calligraphy
A calico cat sitting serenely among vibrant Japanese watercolor style flowers under a large red sun with elegant ink wash effects.
Close-up of a girl with shiny hair and clear skin, eyes closed.
Anime girl with long blonde hair in a traditional Japanese school uniform with a blue bow
A white tiger and a girl in traditional clothing on a misty mountain background. AI generated image using stable diffusion.
A dramatic scene with a lone samurai standing on water, facing a traditional Japanese pagoda in the distance under a stormy sky with swirling clouds and mist, generated using Stable Diffusion.
AI generated image using Stable Diffusion of a beautiful woman dressed in traditional Chinese attire with flowing hair, detailed ancient clothing, and a serene oriental background with a pagoda and foliage.